Skip to content

Ait

v0.38.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-harness agent-isolation agentic ai-agents ai-coding ai-tools
+14 more
aider claude-code code-provenance codex coding-assistant cursor developer-tools gemini-cli git git-worktree llm-agents python vcs worktree

Summary

AI summary

Quickstart now clarifies direnv allow is only needed when prompted.

Full changelog

0.38.0

This release makes human-facing readiness clearer while preserving JSON automation contracts.

  • Text ait status now starts with the direct answer: whether the agent CLI is ready, or the one action needed such as direnv allow or ait init.
  • The previous detailed text line is now Agent CLI detail; JSON agent_cli_ready and agent_cli_message are unchanged.
  • Quickstart wording now says direnv allow is only needed if prompted.
  • Release smoke coverage now invokes the generated wrapper directly and verifies policy recreation, agent-memory import, attempt-memory creation, workspace output, and attempt commit creation.

Validation:

  • .venv/bin/pytest -q -> 248 passed, 4 subtests passed
  • .venv/bin/python -m compileall -q src tests
  • git diff --check
  • .venv/bin/python -m build
  • .venv/bin/python -m twine check dist/*
  • Clean wheel smoke that invoked .ait/bin/claude directly and verified memory policy recreation, CLAUDE.md import, attempt memory, workspace output, and attempt commit creation

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Ait

Get notified when new releases ship.

Sign up free

Related context

Earlier breaking changes

  • v0.55.52 Keep the built-in claude-code reviewer pinned to the local claude -p CLI even when repository policy defines a conflicting command override.

Beta — feedback welcome: [email protected]